© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 8057
    Prev
    Next
    INDEX
    Explanations

    Code and URLs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æıIJéĹ®
    -0.27
    izable
    -0.26
    翳
    -0.25
     Permissions
    -0.24
    lbrace
    -0.24
    çķĻä¸ĭ
    -0.23
    ót
    -0.23
     control
    -0.23
    åİŁåĽłæĺ¯
    -0.23
    claimer
    -0.23
    POSITIVE LOGITS
    adium
    0.31
    æ®ī
    0.28
     Stuff
    0.28
    åij½
    0.27
     rever
    0.25
    acha
    0.24
     manslaughter
    0.24
    ateurs
    0.24
    owitz
    0.23
    ÙħÙĩ
    0.23
    Activations Density 0.095%

    No Known Activations